[
https://issues.apache.org/jira/browse/HDFS-13880?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16599315#comment-16599315
]
Konstantin Shvachko commented on HDFS-13880:
--------------------------------------------
Following up on that thought. I have the following three candidate terms to
replace "Masync":
# _uncoordinated_ - meaning that the operation should not be coordinated with
the sequence of metadata updates, outside of GSI.
# _asynchronous_ - just indicates no msync-wait
# _server-local_ - meaning that it accesses the server local state rather than
the global metadata state
LMK if there are other options? I am in favor of _uncoordinated_.
Another thought that write operations can also be global and local. Like
{{transitionToActive}}, {{transitionToObserver}} are write operations, but
uncoordinated. How do we handle them now with ORPP?
> Add mechanism to allow certain RPC calls to bypass sync
> -------------------------------------------------------
>
> Key: HDFS-13880
> URL: https://issues.apache.org/jira/browse/HDFS-13880
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: namenode
> Reporter: Chen Liang
> Assignee: Chen Liang
> Priority: Major
> Attachments: HDFS-13880-HDFS-12943.001.patch,
> HDFS-13880-HDFS-12943.002.patch
>
>
> Currently, every single call to NameNode will be synced, in the sense that
> NameNode will not process it until state id catches up. But in certain cases,
> we would like to bypass this check and allow the call to return immediately,
> even when the server id is not up to date. One case could be the to-be-added
> new API in HDFS-13749 that request for current state id. Others may include
> calls that do not promise real time responses such as {{getContentSummary}}.
> This Jira is to add the mechanism to allow certain calls to bypass sync.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
